Upload app.py

app.py

@@ -12,8 +12,6 @@ SEED = 42
 NUM_CLASSES = 250
 INPUT_SIZE = 32
 
-cap = cv2.VideoCapture(1)
-
 
 
 # Tensorflow layer to process data in TFLite
@@ -198,6 +196,17 @@ def make_prediction(processed_landmarks):
 # ...
 
 with mp_holistic.Holistic(min_detection_confidence=0.5, min_tracking_confidence=0.5) as holistic:
+    import cv2
+    import numpy as np
+    import gradio as gr
+    from tensorflow import lite as tflite
+    import tensorflow as tf
+    import mediapipe as mp
+
+
+    # ... (Previous code remains the same)
+
+    # Modify the predict_with_webcam function to take an image as input and return the prediction string
     def predict_with_webcam(frame):
         if frame is None:
             raise ValueError("Frame is None. Make sure your webcam is working properly.")
@@ -205,7 +214,9 @@ with mp_holistic.Holistic(min_detection_confidence=0.5, min_tracking_confidence=
         # Make detections using mediapipe
         image, results = mediapipe_detection(frame, holistic)
         print(results)
-        landmarks = extract_keypoints(results)
+
+        if results is not None:
+            landmarks = extract_keypoints(results)
         if landmarks is not None:
             # Calculate the number of landmarks per frame
             landmarks_per_frame = len(landmarks) // (N_ROWS * N_DIMS)
@@ -221,29 +232,40 @@ with mp_holistic.Holistic(min_detection_confidence=0.5, min_tracking_confidence=
         else:
             return "Could not detect landmarks. Make sure your webcam is working properly."
 
-# Set mediapipe model
-while cap.isOpened():
-    # Read feed
-    ret, frame = cap.read()
-    if not ret:
-        print("Failed to capture frame from the webcam.")
-        break
 
-    try:
-        # Make predictions
-        prediction = predict_with_webcam(frame)
+    # Set mediapipe model
+    cap = cv2.VideoCapture(0)
+    while cap.isOpened():
+        # Read feed
+        ret, frame = cap.read()
+        if not ret:
+            print("Failed to capture frame from the webcam.")
+            break
+
+        try:
+            # Make predictions
+            prediction = predict_with_webcam(frame)
 
-        # Display the frame with the prediction
-        cv2.putText(frame, prediction, (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-        cv2.imshow('Webcam Landmark Prediction', frame)
+            # Display the frame with the prediction
+            cv2.putText(frame, prediction, (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+            cv2.imshow('Webcam Landmark Prediction', frame)
 
-    except Exception as e:
-        print("Error occurred:", e)
+        except Exception as e:
+            print("Error occurred:", e)
 
-    # Exit the loop when 'q' key is pressed
-    if cv2.waitKey(1) & 0xFF == ord('q'):
-        break
+        # Exit the loop when 'q' key is pressed
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
 
-cap.release()
-cv2.destroyAllWindows()
+    cap.release()
+    cv2.destroyAllWindows()
+
+    # Define the Gradio interface
+    iface = gr.Interface(
+        fn=predict_with_webcam,  # The function to use for prediction
+        inputs="webcam",  # Use Gradio's "webcam" input to capture frames from the webcam
+        outputs=gr.outputs.Textbox()  # Display the prediction as text
+    )
 
+    # Launch the interface
+    iface.launch()